Ligand-based virtual screening and inductive learning for identification of SIRT1 inhibitors in natural products.

摘要: Sirtuin 1 (SIRT1) is a nicotinamide adenine dinucleotide-dependent deacetylase, and its dysregulation can lead to ageing, diabetes, cancer. From 346 experimentally confirmed SIRT1 inhibitors, an inhibitor structure pattern was generated by inductive logic programming (ILP) with DMax Chemistry Assistant software. The contained amide, amine, hetero-aromatic five-membered rings, each of which had hetero-atom unsubstituted atom at distance 2. According this pattern, ligand-based virtual screening 444 880 active compounds from Chinese herbs identified 12 as inhibitors SIRT1. Three (ZINC08790006, ZINC08792229, ZINC08792355) high affinity (-7.3, -7.8, -8.6 kcal/mol, respectively) for estimated molecular docking software AutoDock Vina. This study demonstrated use ILP background knowledge in machine learning facilitate screening.